US House Prices Research Articles

Investigation of Influential Factors of Housing Price

The fluctuation of housing prices and its influencing factors are important research topics in economics. Under the current background of rapid globalization and urbanization, understanding the driving factors of housing prices is not only an important contribution to academic research but also has important guiding significance for policymakers and individual home buyers. This paper explores the key factors affecting housing prices, focusing on the impact of variables such as living space, land space, housing landscape, housing conditions, housing quality, and housing construction year on housing prices. This study uses multiple regression analysis to analyze the US housing price data set. The results show that living space, housing landscape, housing quality, and housing construction year have statistically significant effects on housing prices at a significance level of 1%. This study provides an effective reference to real estate developers, policymakers, and individual home buyers, which can help them understand market demand more deeply, make decisions that are more in line with market trends, and promote the dynamic and functional development of the real estate market.

Housing search activity and quantiles-based predictability of housing price movements in the USA

Purpose Recent evidence from a linear econometric framework infers that housing search activity, captured from Google Trends data, can predict housing returns for the USA at a national and regional (metropolitan statistical area [MSA]) level. Based on search theory, the authors, however, postulate that search activity can also predict housing returns volatility. This study aims to explore the possibility of using online search activity to predict both housing returns and volatility. Design/methodology/approach Using a k-th order non-parametric causality-in-quantiles test allows us to test for predictability in a robust manner over the entire conditional distribution of both housing price returns and its volatility (i.e. squared returns) by controlling for nonlinearity and structural breaks that exist in the data. Findings The analysis over the monthly period of 2004:01 to 2021:01 produces results indicating that while housing search activity continues to predict aggregate US house price returns, barring the extreme ends of the conditional distribution, volatility is relatively strongly predicted over the entire quantile range considered. The results carry over to an alternative (the generalized autoregressive conditional heteroskedasticity-based) metric of volatility, higher (weekly)-frequency data (over January 2018–March 2021) and to over 84% of the 77 MSAs considered. Originality/value To the best of the authors’ knowledge, this is the first study regarding predictability of overall and regional US housing price returns and volatility using search activity, based on a non-parametric higher-order causality-in-quantiles framework, which is insightful to investors, policymakers and academics.

The impact of US housing demand and supply shocks on the Australian economy: Analysis implementing a SVAR model

AbstractThis thesis develops an open economy structural vector autoregression model to determine how the Australian economy is affected by both a US housing demand shock and a US housing supply shock. Previous literature has either grouped Australia with other economies or has excluded Australia altogether. This leaves a significant literature gap in explaining how the Australian economy is solely impacted. The results of the model indicate both a US housing demand and a US housing supply shock significantly impact the Australian economy, with the most significant being the impact of a US house price shock upon Australian GDP which is large and persistent over time. The results contribute to the understanding of how Australian policymakers should incorporate the US housing market into policy decisions and central bank modelling.

Are younger buyers driving the housing boom? A geographic perspective on US home purchases, 2018-2021

ABSTRACT Rapid growth in US housing prices has coincided with the large Millennial demographic group reaching peak homebuying age, leading some to speculate that new demand from younger buyers is putting upward pressure on home prices. This Research Note uses data from the Home Mortgage Disclosure Act mortgage data to examine where younger buyers are purchasing homes. Data show that the share of buyers under age 35 fell in more than half of US counties, including 45% of metropolitan counties. A county- and MSA-level regression analysis finds a null or slightly negative correlation between changes in the share of buyers under age 35 and changes in home prices, and a small positive effect on debt-to-income ratios from 2018 to 2021, providing little to no evidence that young buyers are pushing up home prices.

Influence Factor Analysis and Forecast of US House Prices Based on Linear Regression and Time Series

In the United States, house prices remain a perennial topic of interest for every resident. Beyond influencing individual housing choices, fluctuations in house prices play a pivotal role in shaping pleasant lifestyles and ensuring the nation's stable economic growth. The housing market, in fact, underpins the entire U.S. economic system. This study employed a multifaceted approach, utilizing both multiple linear regression models and time series analysis, to delve deeply into the factors influencing U.S. house prices. The research identified that residential construction spending and GDP are the most significant drivers leading to an increase in the American House Price Index (HPI). Additionally, through time series analysis, various graphical representations were constructed to visualize the quarterly trends in the American HPI, rendering the findings more comprehensible. In essence, this research offers a scientific foundation for future adjustments in housing price policies. It holds substantial relevance for all stakeholders in the real estate market, from buyers and sellers to developers and policymakers.

The marginal cost of mortality risk reduction: Evidence from housing markets

We provide the first evidence on the rate at which spatial variation in all-cause mortality risk is capitalized into US housing prices. Using a hedonic framework, we recover the annual implicit cost of a 0.1 percentage-point reduction in mortality risk among older Americans and find that this cost is less than $3453 for a 67 year old and decreasing with age to less than $629 for an 87 year old. These estimates, while similar to estimates from the market for health care, are far below comparable estimates from markets for labor and automobiles, suggesting that the housing market provides an alternative, substantially cheaper channel for reducing mortality risk. We find this conclusion to be robust to a wide range of econometric model specifications, including accounting for associated expenditures on property taxes and the physical and financial costs of moving.

US housing prices and the transmission mechanism of connectedness

This research examines the connectedness effects of US house prices across different metropolitan areas, utilizing a quantile connectedness model. We identify MSAs that could play a significant role in the transmission of house prices, either as net contributors or recipients of these effects. The level of quantiles emerges as another crucial factor, influencing the behavior of various metropolitan areas across different house price ranges. Denver, Los Angeles, Seattle, Phoenix, San Diego, and San Francisco exhibit net-contributing behavior, whereas Chicago, Detroit, Las Vegas, Minneapolis, New York, and Atlanta show a net-receiving trend. Metropolitan areas like Portland, Boston, Charlotte, Cleveland, Dallas, Miami, Tampa, and Washington display roles that can either be contributing or receiving over the time period. Lastly, external factors such as economic crises or health events like the Covid-19 outbreak play a pivotal role in shaping MSAs' behavior.

Time-varying volatility and the housing market

AbstractThis paper studies the role of stochastic volatility in a setting where housing serves as an important propagation mechanism. After showing time-varying volatility in US house prices, we estimate a dynamic stochastic general equilibrium model with housing, financial frictions, and stochastic volatility using a nonlinear approximation and Bayesian econometric techniques. Incorporating stochastic volatility into the model greatly improves model fit and accounts for approximately half of the increased volatility in house prices observed during the Great Recession. Increased stochastic volatility escalates uncertainty which has significant effects on macroeconomic variables. While uncertainty in most sectors has negative effects on the economy, uncertainty on collateral constraints has the largest role. Unlike other uncertainty shocks, the housing demand uncertainty creates positive spillovers in the economy. Credit conditions, adjustment costs of capital and housing, and monetary policy are important transmission mechanisms for the stochastic volatility shocks.

Nature of comovements in US state and MSA housing prices

AbstractThis study analyzes the time‐varying nature and determinants of comovements in US housing prices using state and metropolitan statistical area (MSA) data. We employ dynamic factor models with time‐varying loadings and stochastic volatility (DFM‐TV‐SV) to estimate the national, regional, and state factors. The time‐varying factor loadings and stochastic volatility features enrich the dynamic factor model structures and are an effective tool to examine the comovements in housing prices. We find that the national factor is the dominant factor in explaining the movement of housing prices. The national factor accounts for 79% of the variation in state‐level housing prices on average, with the greatest magnitude occurring during the housing boom and bust periods in many regions and states. We also find that the factors and synchronization effects are time‐varying and heterogeneous across regions. The state‐level housing prices contain higher national housing factor components in states with more diverse economies, higher wages and house prices, and lower unemployment rates. These findings shed light on the effectiveness of residential real estate diversification across the United States and the potential for elevated national housing risk amid economic downturns due to increased national housing price integration.

Research on the Prediction of US House Prices Based on Machine Learning

With the increase in the standard, houses have become an indispensable part of people’s lives. However, purchasing houses needs to consider the prices. Therefore, this paper uses machine learning to predict US house prices. Based on the random forest and linear regression method used in this research. It is found that the use of the former has a good effect on predicting multivariate nonlinear relationships in house prices. After comparing the results of actual prices and predicting prices, residents can select different room structures by contrasting them with experimental types as the numerical results are basically accurate. This research provides theoretical value to the literature on housing price prediction and brings different enlightenment to policymakers, regulators, and investors. As a result, this research plays a key role in maintaining the order of the real estate market and helping people make good choices.

Leveraging Data Analytics Methods For Statistical (ANOVA) Analysis of Factors Influencing US Housing Prices

Leveraging Data Analytics Methods For Statistical (ANOVA) Analysis of Factors Influencing US Housing Prices

Bayesian inference in spatial GARCH models: an application to US house price returns

ABSTRACT In this paper we consider a high-order spatial generalized autoregressive conditional heteroskedasticity (GARCH) model to account for the volatility clustering patterns observed over space. The model consists of a log-volatility equation that includes the high-order spatial lags of the log-volatility term and the squared outcome variable. We use a transformation approach to turn the model into a mixture of normals model, and then introduce a Bayesian Markov chain Monte Carlo (MCMC) estimation approach coupled with a data-augmentation technique. Our simulation results show that the Bayesian estimator has good finite sample properties. We apply a first-order version of the spatial GARCH model to US house price returns at the metropolitan statistical area level over the period 2006Q1–2013Q4 and show that there is significant variation in the log-volatility estimates over space in each period.

Time‐varying impacts of expectations on housing markets across hot and cold phases

AbstractThis study investigates time‐varying roles of people's expectations in driving the US housing price and quantity dynamics using a Threshold Vector Autoregressive model. The expectation measure, a good‐time‐to‐buy (GTTB) index, works as the threshold indicator to classify pessimism and optimism phases, and represents the model‐based measure of uncertainty. There is strong evidence for regime switches in responses to shocks across the two phases. The results show that good and bad shocks play similar roles in housing markets. Tiny responses of GTTB to both large good and bad shocks in the two regimes suggest “too bad to be believed” and “too good to be believed” patterns. The estimation is biased as volatility shocks are neglected in the housing boom and bust.

Shifting Drivers for US House Prices

Historically, US house prices track key housing and economic factors such as housing starts, housing inventory, employment, interest rates, and consumer price indices, to name a few. During the past two years, the US economy has gyrated through myriad distortions resulting from the government’s various attempts to control the pandemic. Most recently, the administration has adopted policies that have further disrupted the economy, leading to increases in consumer prices and shortages of goods. We study the potential change in the connection between US house prices and key drivers before and after the onset of the pandemic. We take several approaches to this question, including studying cross-correlations of the multivariate time series, estimating a seasonal ARIMA model, and fitting seemingly unrelated regressions. Finally, we model house prices as a univariate time series. We find some evidence of a change in the association between house prices and other economic measures from before to after the covid response.

US House Prices by Census Division: Persistence, Trends and Structural Breaks

US House Prices by Census Division: Persistence, Trends and Structural Breaks

US Bilateral Capital Inflows and Housing Price Return Predictability

US Bilateral Capital Inflows and Housing Price Return Predictability

Modelling Returns in US Housing Prices—You’re the One for Me, Fat Tails

In this paper, we analysed the heavy-tailed behaviour in the dynamics of housing-price returns in the United States. We investigated the sources of heavy tails by estimating autoregressive models in which innovations can be subject to GARCH effects and/or non-Gaussianity. Using monthly data from January 1954 to September 2019, the properties of the models were assessed both within- and out-of-sample. We found strong evidence in favour of modelling both GARCH effects and non-Gaussianity. Accounting for these properties improves within-sample performance as well as point and density forecasts.

On the Creation and Destruction of National Wealth: Are Financial Collapses Endogenous?

This paper traces US national wealth from 1914 through 2015 and constructs a multivariate econometric model that combines elements of short-term and long-term dynamics. We find that US wealth depends on a range of macroeconomic variables, including the wealth itself observed in the previous period, change in market capitalization, change in US house price index and inflation. Less impactful, statistically significant factors included unemployment, changes in oil price, and change in debt-to-GDP ratio. Another significant result is that the Glass–Steagall Act, which prohibited commercial banks from speculative activity in the stock market after 1933, had a statistically significant positive impact on wealth in the US. We test the model by asking whether it could have anticipated the actual collapse in 2008, given prior data up to 2000, 2005 and 2010. All three tests forecasted a sharp wealth decline starting in 2008, followed by a recovery. These results suggest the possibility of forecasting future financial collapses. We have found our model to be slightly more accurate in the short run than in the long run.

Leading indicators for US house prices: New evidence and implications for EU financial risk managers

AbstractThis study draws on machine learning as a means to causal inference for econometric investigation. We utilize the concept of transfer entropy to examine the relationship between the US National Association of Home Builders Index and the S&P CoreLogic Case‐Shiller 20 City Composite Home Price Index (SPCS20). The empirical evidence implies that the survey data can help to predict US house prices. This finding extends the results of Granger causality tests performed by Rodriguez Gonzalez et al. in 2018 using a new machine learning approach that methodologically differs from traditional methods in empirical financial research.

Ignoring Spatial and Spatiotemporal Dependence in the Disturbances Can Make Black Swans Appear Grey

Automated valuation models (AVMs) are widely used by financial institutions to estimate the property value for a residential mortgage. The distribution of pricing errors obtained from AVMs generally show fat tails (Pender 2016; Demiroglu and James Management Science, 64(4), 1747–1760 2018). The extreme events on the tails are usually known as “black swans” (Taleb 2010) in finance and their existence complicates financial risk management, assessment, and regulation. We show via theory, Monte Carlo experiments, and an empirical example that a direct relation exists between non-normality of the pricing errors and goodness-of-fit of the house pricing models. Specifically, we provide an empirical example using US housing prices where we demonstrate an almost perfect linear relation between the estimated degrees-of-freedom for a Student’s t distribution and the goodness-of-fit of sophisticated evaluation models with spatial and spatialtemporal dependence.